Skip to content

Instantly share code, notes, and snippets.

@darthgera123

darthgera123/DOTAW_baseline.ipynb

Created March 27, 2020 11:17
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save darthgera123/73fbe516c7e3d3aea1c0f7f26dd6f7d5 to your computer and use it in GitHub Desktop.
Save darthgera123/73fbe516c7e3d3aea1c0f7f26dd6f7d5 to your computer and use it in GitHub Desktop.
Download ZIP
Baseline for DOTAW
Display the source blob
Display the rendered blob
Raw
DOTAW_baseline.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Baseline for the challenge DOTAW"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn.model_selection import train_test_split \n",
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn import metrics"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load Data"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"train_data = pd.read_csv('../data/public/train.csv')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Analyse Data"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>winner</th>\n",
" <th>cluster_id</th>\n",
" <th>game_mode</th>\n",
" <th>game_type</th>\n",
" <th>hero_0</th>\n",
" <th>hero_1</th>\n",
" <th>hero_2</th>\n",
" <th>hero_3</th>\n",
" <th>hero_4</th>\n",
" <th>hero_5</th>\n",
" <th>...</th>\n",
" <th>hero_103</th>\n",
" <th>hero_104</th>\n",
" <th>hero_105</th>\n",
" <th>hero_106</th>\n",
" <th>hero_107</th>\n",
" <th>hero_108</th>\n",
" <th>hero_109</th>\n",
" <th>hero_110</th>\n",
" <th>hero_111</th>\n",
" <th>hero_112</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>-1</td>\n",
" <td>223</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>152</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>-1</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>131</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>-1</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>154</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>-1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>-1</td>\n",
" <td>171</td>\n",
" <td>2</td>\n",
" <td>3</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>-1</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 117 columns</p>\n",
"</div>"
],
"text/plain": [
" winner cluster_id game_mode game_type hero_0 hero_1 hero_2 hero_3 \\\n",
"0 -1 223 2 2 0 0 0 0 \n",
"1 1 152 2 2 0 0 0 1 \n",
"2 1 131 2 2 0 0 0 1 \n",
"3 1 154 2 2 0 0 0 0 \n",
"4 -1 171 2 3 0 0 0 0 \n",
"\n",
" hero_4 hero_5 ... hero_103 hero_104 hero_105 hero_106 hero_107 \\\n",
"0 0 0 ... 0 0 0 0 0 \n",
"1 0 -1 ... 0 0 0 0 0 \n",
"2 0 -1 ... 0 0 0 0 0 \n",
"3 0 0 ... -1 0 0 0 0 \n",
"4 0 -1 ... 0 0 0 0 0 \n",
"\n",
" hero_108 hero_109 hero_110 hero_111 hero_112 \n",
"0 0 0 0 0 0 \n",
"1 0 0 0 0 0 \n",
"2 0 0 0 0 0 \n",
"3 0 0 0 0 0 \n",
"4 0 0 0 0 0 \n",
"\n",
"[5 rows x 117 columns]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_data.head()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>winner</th>\n",
" <th>cluster_id</th>\n",
" <th>game_mode</th>\n",
" <th>game_type</th>\n",
" <th>hero_0</th>\n",
" <th>hero_1</th>\n",
" <th>hero_2</th>\n",
" <th>hero_3</th>\n",
" <th>hero_4</th>\n",
" <th>hero_5</th>\n",
" <th>...</th>\n",
" <th>hero_103</th>\n",
" <th>hero_104</th>\n",
" <th>hero_105</th>\n",
" <th>hero_106</th>\n",
" <th>hero_107</th>\n",
" <th>hero_108</th>\n",
" <th>hero_109</th>\n",
" <th>hero_110</th>\n",
" <th>hero_111</th>\n",
" <th>hero_112</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>92650.000000</td>\n",
" <td>92650.000000</td>\n",
" <td>92650.000000</td>\n",
" <td>92650.000000</td>\n",
" <td>92650.000000</td>\n",
" <td>92650.000000</td>\n",
" <td>92650.000000</td>\n",
" <td>92650.000000</td>\n",
" <td>92650.000000</td>\n",
" <td>92650.000000</td>\n",
" <td>...</td>\n",
" <td>92650.000000</td>\n",
" <td>92650.000000</td>\n",
" <td>92650.000000</td>\n",
" <td>92650.000000</td>\n",
" <td>92650.0</td>\n",
" <td>92650.000000</td>\n",
" <td>92650.000000</td>\n",
" <td>92650.000000</td>\n",
" <td>92650.000000</td>\n",
" <td>92650.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>0.053038</td>\n",
" <td>175.864145</td>\n",
" <td>3.317572</td>\n",
" <td>2.384587</td>\n",
" <td>-0.001630</td>\n",
" <td>-0.000971</td>\n",
" <td>0.000691</td>\n",
" <td>-0.000799</td>\n",
" <td>-0.002008</td>\n",
" <td>0.003173</td>\n",
" <td>...</td>\n",
" <td>-0.001371</td>\n",
" <td>-0.000950</td>\n",
" <td>0.000885</td>\n",
" <td>0.000594</td>\n",
" <td>0.0</td>\n",
" <td>0.001025</td>\n",
" <td>0.000648</td>\n",
" <td>-0.000227</td>\n",
" <td>-0.000043</td>\n",
" <td>0.000896</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>0.998598</td>\n",
" <td>35.658214</td>\n",
" <td>2.633070</td>\n",
" <td>0.486833</td>\n",
" <td>0.402004</td>\n",
" <td>0.467672</td>\n",
" <td>0.165052</td>\n",
" <td>0.355393</td>\n",
" <td>0.329348</td>\n",
" <td>0.483950</td>\n",
" <td>...</td>\n",
" <td>0.535024</td>\n",
" <td>0.206112</td>\n",
" <td>0.283985</td>\n",
" <td>0.155940</td>\n",
" <td>0.0</td>\n",
" <td>0.220703</td>\n",
" <td>0.204166</td>\n",
" <td>0.168707</td>\n",
" <td>0.189868</td>\n",
" <td>0.139033</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>-1.000000</td>\n",
" <td>111.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>...</td>\n",
" <td>-1.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>0.0</td>\n",
" <td>-1.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>-1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>-1.000000</td>\n",
" <td>152.000000</td>\n",
" <td>2.000000</td>\n",
" <td>2.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>1.000000</td>\n",
" <td>156.000000</td>\n",
" <td>2.000000</td>\n",
" <td>2.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>1.000000</td>\n",
" <td>223.000000</td>\n",
" <td>2.000000</td>\n",
" <td>3.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>1.000000</td>\n",
" <td>261.000000</td>\n",
" <td>9.000000</td>\n",
" <td>3.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>...</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.0</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>8 rows × 117 columns</p>\n",
"</div>"
],
"text/plain": [
" winner cluster_id game_mode game_type hero_0 \\\n",
"count 92650.000000 92650.000000 92650.000000 92650.000000 92650.000000 \n",
"mean 0.053038 175.864145 3.317572 2.384587 -0.001630 \n",
"std 0.998598 35.658214 2.633070 0.486833 0.402004 \n",
"min -1.000000 111.000000 1.000000 1.000000 -1.000000 \n",
"25% -1.000000 152.000000 2.000000 2.000000 0.000000 \n",
"50% 1.000000 156.000000 2.000000 2.000000 0.000000 \n",
"75% 1.000000 223.000000 2.000000 3.000000 0.000000 \n",
"max 1.000000 261.000000 9.000000 3.000000 1.000000 \n",
"\n",
" hero_1 hero_2 hero_3 hero_4 hero_5 \\\n",
"count 92650.000000 92650.000000 92650.000000 92650.000000 92650.000000 \n",
"mean -0.000971 0.000691 -0.000799 -0.002008 0.003173 \n",
"std 0.467672 0.165052 0.355393 0.329348 0.483950 \n",
"min -1.000000 -1.000000 -1.000000 -1.000000 -1.000000 \n",
"25% 0.000000 0.000000 0.000000 0.000000 0.000000 \n",
"50% 0.000000 0.000000 0.000000 0.000000 0.000000 \n",
"75% 0.000000 0.000000 0.000000 0.000000 0.000000 \n",
"max 1.000000 1.000000 1.000000 1.000000 1.000000 \n",
"\n",
" ... hero_103 hero_104 hero_105 hero_106 \\\n",
"count ... 92650.000000 92650.000000 92650.000000 92650.000000 \n",
"mean ... -0.001371 -0.000950 0.000885 0.000594 \n",
"std ... 0.535024 0.206112 0.283985 0.155940 \n",
"min ... -1.000000 -1.000000 -1.000000 -1.000000 \n",
"25% ... 0.000000 0.000000 0.000000 0.000000 \n",
"50% ... 0.000000 0.000000 0.000000 0.000000 \n",
"75% ... 0.000000 0.000000 0.000000 0.000000 \n",
"max ... 1.000000 1.000000 1.000000 1.000000 \n",
"\n",
" hero_107 hero_108 hero_109 hero_110 hero_111 \\\n",
"count 92650.0 92650.000000 92650.000000 92650.000000 92650.000000 \n",
"mean 0.0 0.001025 0.000648 -0.000227 -0.000043 \n",
"std 0.0 0.220703 0.204166 0.168707 0.189868 \n",
"min 0.0 -1.000000 -1.000000 -1.000000 -1.000000 \n",
"25% 0.0 0.000000 0.000000 0.000000 0.000000 \n",
"50% 0.0 0.000000 0.000000 0.000000 0.000000 \n",
"75% 0.0 0.000000 0.000000 0.000000 0.000000 \n",
"max 0.0 1.000000 1.000000 1.000000 1.000000 \n",
"\n",
" hero_112 \n",
"count 92650.000000 \n",
"mean 0.000896 \n",
"std 0.139033 \n",
"min -1.000000 \n",
"25% 0.000000 \n",
"50% 0.000000 \n",
"75% 0.000000 \n",
"max 1.000000 \n",
"\n",
"[8 rows x 117 columns]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_data.describe()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Split Data into Train and Validation"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"X = train_data.drop('winner',1)\n",
"y = train_data['winner']\n",
"# Validation testing\n",
"X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Define the Classifier and Train"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/gera/anaconda3/lib/python3.6/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.\n",
" FutureWarning)\n"
]
},
{
"data": {
"text/plain": [
"LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
" intercept_scaling=1, l1_ratio=None, max_iter=100,\n",
" multi_class='warn', n_jobs=None, penalty='l2',\n",
" random_state=None, solver='warn', tol=0.0001, verbose=0,\n",
" warm_start=False)"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"classifier = LogisticRegression()\n",
"classifier.fit(X_train,y_train)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Predict on Validation"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"y_pred = classifier.predict(X_val)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Actual</th>\n",
" <th>Predicted</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>26389</th>\n",
" <td>1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>55196</th>\n",
" <td>-1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>51250</th>\n",
" <td>-1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25508</th>\n",
" <td>1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24128</th>\n",
" <td>1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2442</th>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5638</th>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3714</th>\n",
" <td>-1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36579</th>\n",
" <td>-1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10399</th>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13464</th>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>71600</th>\n",
" <td>-1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>80162</th>\n",
" <td>1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7077</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>63431</th>\n",
" <td>-1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>78584</th>\n",
" <td>1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31413</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13393</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>90845</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23339</th>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13756</th>\n",
" <td>-1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>63563</th>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>81880</th>\n",
" <td>-1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>77591</th>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23311</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Actual Predicted\n",
"26389 1 -1\n",
"55196 -1 1\n",
"51250 -1 1\n",
"25508 1 -1\n",
"24128 1 -1\n",
"2442 -1 -1\n",
"5638 -1 -1\n",
"3714 -1 1\n",
"36579 -1 1\n",
"10399 -1 -1\n",
"13464 -1 -1\n",
"71600 -1 1\n",
"80162 1 -1\n",
"7077 1 1\n",
"63431 -1 1\n",
"78584 1 -1\n",
"31413 1 1\n",
"13393 1 1\n",
"90845 1 1\n",
"23339 -1 -1\n",
"13756 -1 1\n",
"63563 -1 -1\n",
"81880 -1 1\n",
"77591 -1 -1\n",
"23311 1 1"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.DataFrame({'Actual': y_val, 'Predicted': y_pred})\n",
"df1 = df.head(25)\n",
"df1"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Evaluate the Performance"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"F1 score Error: 0.638888888888889\n",
"ROC AUC Error: 0.5928579002999843\n"
]
}
],
"source": [
"print('F1 score Score:', metrics.f1_score(y_val, y_pred)) \n",
"print('ROC AUC Score:', metrics.roc_auc_score(y_val, y_pred)) "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load Test Set"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"test_data = pd.read_csv('../data/public/test.csv')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Predict Test Set"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"y_test = classifier.predict(test_data)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"df = pd.DataFrame(y_test,columns=['winner'])\n",
"df.to_csv('../data/public/submission.csv',index=False)"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": true
},
"source": [
"To participate in the challenge click [here](https://www.aicrowd.com/challenges/dotaw-dota-2-prediction/)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.10"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment